© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 16409
    Prev
    Next
    INDEX
    Explanations

    phrases related to musical instruments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to musical performance and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Merchants
    -0.80
     insurer
    -0.80
    insured
    -0.79
    redit
    -0.79
    osponsors
    -0.79
     insurers
    -0.79
    Neigh
    -0.78
     insured
    -0.77
     Insurance
    -0.77
     Discount
    -0.76
    POSITIVE LOGITS
     dexterity
    1.29
     improvis
    1.24
     rhythm
    1.24
     multit
    1.16
     improv
    1.11
     dexter
    1.10
     skills
    1.10
     keyboard
    1.06
     teamwork
    1.05
     tempo
    1.05
    Activations Density 1.214%

    No Known Activations